Traffic Forecasting on Traffic Movie Snippets
OPEN ACCESS
Loading...
Author / Producer
Date
2021-10-27
Publication Type
Other Conference Item
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
Advances in traffic forecasting technology can greatly impact urban mobility. In the traffic4cast competition, the task of short-term traffic prediction is tackled in unprecedented detail, with traffic volume and speed information available at 5 minute intervals and high spatial resolution. To improve generalization to unknown cities, as required in the 2021 extended challenge, we propose to predict small quadratic city sections, rather than processing a full-city-raster at once. At test time, breaking down the test data into spatially-cropped overlapping snippets improves stability and robustness of the final predictions, since multiple patches covering one cell can be processed independently. With the performance on the traffic4cast test data and further experiments on a validation set it is shown that patch-wise prediction indeed improves accuracy. Further advantages can be gained with a Unet++ architecture and with an increasing number of patches per sample processed at test time. We conclude that our snippet-based method, combined with other successful network architectures proposed in the competition, can leverage performance, in particular on unseen cities. All source code is available at https://github.com/NinaWie/NeurIPS2021-traffic4cast.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
Pages / Article No.
Publisher
ETH Zurich
Event
Traffic4cast @ NeurIPS 2021
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
TRAFFIC FORECASTINGS (TRANSPORTATION AND TRAFFIC); Image analysis
Organisational unit
03901 - Raubal, Martin / Raubal, Martin
Notes
This report documents our solution for the NeurIPS 2021 Traffic4cast competition. The paper is published on arXiv and was except for presentation at the NeurIPS workshop.
Funding
Related publications and datasets
Is new version of: